Publication Date
In 2025 | 1 |
Descriptor
Artificial Intelligence | 1 |
Correlation | 1 |
Observation | 1 |
Prediction | 1 |
Research Design | 1 |
Sample Size | 1 |
Social Science Research | 1 |
Statistical Analysis | 1 |
Statistical Inference | 1 |
Source
Sociological Methods &… | 1 |
Publication Type
Journal Articles | 1 |
Reports - Research | 1 |
Education Level
Audience
Location
Laws, Policies, & Programs
Assessments and Surveys
What Works Clearinghouse Rating
David Broska; Michael Howes; Austin van Loon – Sociological Methods & Research, 2025
Large language models (LLMs) provide cost-effective but possibly inaccurate predictions of human behavior. Despite growing evidence that predicted and observed behavior are often not "interchangeable," there is limited guidance on using LLMs to obtain valid estimates of causal effects and other parameters. We argue that LLM predictions…
Descriptors: Artificial Intelligence, Observation, Prediction, Correlation